Lesson 13 Sorting

import pandas as pd

df = pd.read_csv(
    "https://raw.githubusercontent.com/noahgift/food/master/data/features.en.openfoodfacts.org.products.csv")
df.drop(["Unnamed: 0", "exceeded", "g_sum", "energy_100g"], axis=1, inplace=True) #drop two rows we don't need
df = df.drop(df.index[[1,11877]]) #drop outlier
df.rename(index=str, columns={"reconstructed_energy": "energy_100g"}, inplace=True)
df.head()

food_facts = list(df.columns.values)
food_facts

sorted(food_facts)

sorted(food_facts, reverse=True)

food_facts = list(df.columns.values)
print(f"Before sort: {food_facts}")
food_facts.sort()
print(f"After sort: {food_facts}")

food_facts = list(df.columns.values)

%%timeit -n 3 -r 3
food_facts.sort()

food_facts = list(df.columns.values)

%%timeit -n 3 -r 3
sorted(food_facts)

food_facts_row = df.head(1).to_dict()
food_facts_row

sorted(food_facts_row, reverse=True)

df["product"].head().values

def dataframe_rows(df=df, column="product", chunks=10):
  
    count_row = df.shape[0]
    rows = list(df[column].values)
    for i in range(0, count_row, chunks):
      yield rows[i:i + chunks]
    
    

rows = dataframe_rows()
next(rows)

next(rows)

sorted_row = (sorted(row) for row in rows )
print(next(sorted_row))

food_items = ['Chocolate Nut Crunch', 'Cranberries', 'Curry Lentil Soup Mix', 
                'Milk Chocolate Peanut Butter Malt Balls', 'Organic Harvest Pilaf', 
                'Organic Tamari Pumpkin Seed', 'Split Pea Soup Mix', 
                'Swiss-Style Muesli', "Whole Wheat 'N Honey Fig Bars", 
                'Yogurt Pretzels']

from random import sample

def shuffle_list(items):
  """Randomly Shuffles List"""
  
  shuffled = sample(items, len(items))
  return shuffled
  

shuffled_food_items = shuffle_list(food_items)
shuffled_food_items

def best_snack(item):
  if item == "Chocolate Nut Crunch":
    return 1
  return len(item) 

sorted(shuffled_food_items, key=best_snack)

class Food:
  def __init__(self, product, protein):
    self.product = product
    self.protein = protein
  def __repr__(self):
    return f"Food: {self.product}, Protein: {self.protein}"

pairs = df[["product", "proteins_100g"]].head().values.tolist()
pairs

pairs = df[["product", "proteins_100g"]].head().values.tolist()
foods = [Food(item[0], item[1]) for item in pairs]
foods

sorted(foods, key=lambda food: food.protein)

foods[0].__dict__
type(foods[0])

df.sort_values(by=["carbohydrates_100g"], ascending=False).head(5)

df.sort_values(by=["fat_100g", "salt_100g"], ascending=[False, False]).head(10)

def high_protein(row):
  """Creates a high or low protein category"""
  
  if row > 80:
    return "high_protein"
  return "low_protein"

df["high_protein"] = df["proteins_100g"].apply(high_protein)
df.head()

df.groupby("high_protein").median()

df.groupby("high_protein").describe()